English
Related papers

Related papers: Saffron-1: Safety Inference Scaling

200 papers

Scaling test-time computation with reinforcement learning (RL) has emerged as a reliable path to improve large language models (LLM) reasoning ability. Yet, outcome-based reward often incentivizes models to be overconfident, leading to…

Machine Learning · Computer Science 2026-04-28 Liaoyaqi Wang , Chunsheng Zuo , William Jurayj , Benjamin Van Durme , Anqi Liu

While explicit Chain-of-Thought (CoT) empowers large reasoning models (LRMs), it enables the generation of riskier final answers. Current alignment paradigms primarily rely on externally enforced compliance, optimizing models to detect…

Artificial Intelligence · Computer Science 2026-05-12 Yi Zhang , Yuxin Chen , Leheng Sheng , Dongcheng Zhang , Chaochao Lu , Xiang Wang , An Zhang

Large Reasoning Models (LRMs) have become powerful tools for complex problem solving, but their structured reasoning pathways can lead to unsafe outputs when exposed to harmful prompts. Existing safety alignment methods reduce harmful…

Artificial Intelligence · Computer Science 2025-10-24 Wonje Jeung , Sangyeon Yoon , Minsuk Kahng , Albert No

The rapid advancement of multi-modal large reasoning models (MLRMs) -- enhanced versions of multimodal language models (MLLMs) equipped with reasoning capabilities -- has revolutionized diverse applications. However, their safety…

Machine Learning · Computer Science 2025-04-15 Junfeng Fang , Yukai Wang , Ruipeng Wang , Zijun Yao , Kun Wang , An Zhang , Xiang Wang , Tat-Seng Chua

Large Reasoning Models (LRMs) have exhibited extraordinary prowess in tasks like mathematics and coding, leveraging their advanced reasoning capabilities. Nevertheless, as these capabilities progress, significant concerns regarding their…

Computation and Language · Computer Science 2025-05-27 Cheng Wang , Yue Liu , Baolong Bi , Duzhen Zhang , Zhong-Zhi Li , Yingwei Ma , Yufei He , Shengju Yu , Xinfeng Li , Junfeng Fang , Jiaheng Zhang , Bryan Hooi

Present day LLMs face the challenge of managing affordance-based safety risks-situations where outputs inadvertently facilitate harmful actions due to overlooked logical implications. Traditional safety solutions, such as scalar…

Computation and Language · Computer Science 2025-08-11 Sayantan Adak , Pratyush Chatterjee , Somnath Banerjee , Rima Hazra , Somak Aditya , Animesh Mukherjee

Although Large Reasoning Models (LRMs) have progressed in solving complex problems, their chain-of-thought (CoT) reasoning often contains harmful content that can persist even when the final responses appear safe. We show that this issue…

Artificial Intelligence · Computer Science 2026-03-03 Yichi Zhang , Yue Ding , Jingwen Yang , Tianwei Luo , Dongbai Li , Ranjie Duan , Qiang Liu , Hang Su , Yinpeng Dong , Jun Zhu

Reinforcement learning (RL) based post-training for explicit chain-of-thought (e.g., GRPO) improves the reasoning ability of multimodal large-scale reasoning models (MLRMs). But recent evidence shows that it can simultaneously degrade…

Computation and Language · Computer Science 2026-02-12 Soumya Suvra Ghosal , Souradip Chakraborty , Vaibhav Singh , Furong Huang , Dinesh Manocha , Amrit Singh Bedi

Many inference services based on large language models (LLMs) pose a privacy concern, either revealing user prompts to the service or the proprietary weights to the user. Secure inference offers a solution to this problem through secure…

Cryptography and Security · Computer Science 2024-08-08 Deevashwer Rathee , Dacheng Li , Ion Stoica , Hao Zhang , Raluca Popa

Large language models (LLMs) demand considerable computational, energy, and financial resources during both training and deployment. While scaling laws for training have guided much of the field's recent progress, inference costs now…

Machine Learning · Computer Science 2025-07-11 Austin R. Ellis-Mohr , Anuj K. Nayak , Lav R. Varshney

Safeguarding vision-language models (VLMs) is a critical challenge, as existing methods often suffer from over-defense, which harms utility, or rely on shallow alignment, failing to detect complex threats that require deep reasoning. To…

Cryptography and Security · Computer Science 2026-04-03 Nanxi Li , Zhengyue Zhao , G. Edward Suh , Marco Pavone , Chaowei Xiao

Vision-Language Models (VLMs) have achieved remarkable progress in multimodal reasoning tasks through enhanced chain-of-thought capabilities. However, this advancement also introduces novel safety risks, as these models become increasingly…

Computer Vision and Pattern Recognition · Computer Science 2025-10-22 Yinan Xia , Yilei Jiang , Yingshui Tan , Xiaoyong Zhu , Xiangyu Yue , Bo Zheng

Reasoning-based language models have demonstrated strong performance across various domains, with the most notable gains seen in mathematical and coding tasks. Recent research has shown that reasoning also offers significant benefits for…

Artificial Intelligence · Computer Science 2025-05-27 Makesh Narsimhan Sreedhar , Traian Rebedea , Christopher Parisien

Recent advancements in large language models (LLMs) have accelerated progress toward artificial general intelligence, yet their potential to generate harmful content poses critical safety challenges. Existing alignment methods often…

Computation and Language · Computer Science 2025-10-08 Kehua Feng , Keyan Ding , Yuhao Wang , Menghan Li , Fanjunduo Wei , Xinda Wang , Qiang Zhang , Huajun Chen

Large language models (LLMs) and multimodal LLMs are typically safety-aligned before release to prevent harmful content generation. However, recent studies show that safety behaviors are concentrated in a small subset of parameters, making…

Machine Learning · Computer Science 2026-02-13 Zhaoxin Wang , Jiaming Liang , Fengbin Zhu , Weixiang Zhao , Junfeng Fang , Jiayi Ji , Handing Wang , Tat-Seng Chua

Recent studies on the safety alignment of large language models (LLMs) have revealed that existing approaches often operate superficially, leaving models vulnerable to various adversarial attacks. Despite their significance, these studies…

Cryptography and Security · Computer Science 2025-06-02 Jianwei Li , Jung-Eun Kim

In this work, we present the first study to explore inference-time scaling on table reasoning tasks. We develop and evaluate two post-training strategies to enable inference-time scaling: distillation from frontier model reasoning traces…

Computation and Language · Computer Science 2025-09-29 Zheyuan Yang , Lyuhao Chen , Arman Cohan , Yilun Zhao

Large Reasoning Models (LRMs) significantly improve the reasoning ability of Large Language Models (LLMs) by learning to reason, exhibiting promising performance in solving complex tasks. However, their deliberative reasoning process leads…

Computation and Language · Computer Science 2025-08-14 Yue Liu , Jiaying Wu , Yufei He , Ruihan Gong , Jun Xia , Liang Li , Hongcheng Gao , Hongyu Chen , Baolong Bi , Jiaheng Zhang , Zhiqi Huang , Bryan Hooi , Stan Z. Li , Keqin Li

The performance gains of LLMs have historically been driven by scaling up model size and training data. However, the rapidly diminishing availability of high-quality training data is introducing a fundamental bottleneck, shifting the focus…

Computation and Language · Computer Science 2025-10-14 Zhichao Wang , Cheng Wan , Dong Nie

Despite the remarkable proficiency of \textit{Large Reasoning Models} (LRMs) in handling complex reasoning tasks, their reliability in safety-critical scenarios remains uncertain. Existing evaluations primarily assess response-level safety,…

Artificial Intelligence · Computer Science 2025-05-27 Baihui Zheng , Boren Zheng , Kerui Cao , Yingshui Tan , Zhendong Liu , Weixun Wang , Jiaheng Liu , Jian Yang , Wenbo Su , Xiaoyong Zhu , Bo Zheng , Kaifu Zhang